com um clique
claude-cli
Shell out to claude CLI.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Shell out to claude CLI.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Shell out to claude CLI.
Run a multi-agent debate to compare options and converge on a decision.
Run the same task with multiple agents for reviews, critiques, or model comparison.
Autonomous large-task delivery agent. Use for long-running coding work that should go from objective or plan to implemented code, review fixes, PR/MR, and green CI with minimal human-in-the-loop gates.
Manage ClickUp tasks.
Generate a project template for Coolify
| name | claude-cli |
| description | Shell out to claude CLI. |
| allowed-tools | Bash(claude *) |
Use the claude CLI to send prompts to Claude models from shell-based workflows — typically when the current host is OpenCode, or when a sub-agent must run outside the native Agent tool.
claude --model opus --print --output-format text -- "Your prompt here"
Key flags:
--model — model family: opus, sonnet, or haiku.--print — non-interactive; prints response and exits.--output-format text — plain text response; also accepts json, stream-json.-- — separates flags from the prompt (required when the prompt starts with -).claude --model opus --print --output-format text \
--append-system-prompt .tmp/context.md \
-- "Short user-facing prompt here"
--append-system-prompt <file> — appends file content to the system prompt. Use for large shared context (diffs, specs, MR content) without bloating the prompt argument.-- "..." stays brief and human-readable.claude --model opus --print --output-format text \
--effort max \
--name "MBOT: code-review opus" \
-- "Perform the review as instructed."
--effort max — increases thinking budget for complex reasoning tasks.--name "..." — names the session in the Claude UI; useful for auditing batch runs.claude --agent general --model opus --print --output-format text -- "Prompt"
--agent general — uses the general-purpose agent profile with tool access. Omit for a plain completion with no tools.claude --model opus --print --output-format text -- "Prompt" > .tmp/claude-output.txt 2>&1
Redirect to a file for consumption by aggregation steps. Capturing both stdout and stderr (2>&1) avoids lost error messages.
| Flag value | Model |
|---|---|
opus | Claude Opus 4.7 — strongest reasoning |
sonnet | Claude Sonnet 4.6 — balanced speed and quality |
haiku | Claude Haiku 4.5 — fastest, cheapest |
claude CLI is the only path for Claude-family models. Do not use colin-mbot-opus or similar subagents — those are for non-Claude models only.Agent tool; use this CLI as a fallback when the Agent tool is unavailable.claude for any Claude-family model.--print mode does not support interactive tool approval; the agent runs with permissions granted at session level.--append-system-prompt, not inlined in the argument.